Your own app on Flux
Answer “where’s my order?” out loud
Your own app hears a caller, finds their order and tells them where it is, out loud.
“A caller wants to know where their order is. Answer them out loud.”
- TranscriptionLive
- MemoryShipping
- AppsShipping
- ModelLive
- SpeechShipping
Murage- Transcribe the caller$0.003
- Recall the caller: PriyaShipping$0.001
Look up order #5521 on ShopifyShipping$0.010- Draft a reply with fast Mistral$0.001
- Speak the answerShipping$0.003
Examples. Names, prices and costs are illustrative.
What Flux did, step by step
Flux split the ask into jobs and sent each one to the model or tool that fits it. It picks among vetted models for each kind of task, cost-aware.
Transcribe the callerLive
Transcription
Flux turned the caller’s audio into text.
Recall the caller: PriyaShipping
Memory
Memory recalled who was calling.
Look up order #5521 on ShopifyShipping
Apps
The order status came from the store through the Shopify connection.
Draft a reply with fast MistralLive
Model
A short spoken reply needs speed more than depth, so Flux picked a fast model.
Speak the answerShipping
Speech
Flux spoke the answer back to the caller.
Result Priya heard: “Your parcel is out for delivery and arrives on Thursday.”
The receipt
Every call comes back with the model or tool that ran it and what it cost, all on one bill.
These costs are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay its own rate. See pricing
Example receiptIllustrative
| Step | Cost |
|---|---|
| Transcribe the callerTranscription | $0.003 |
| Recall the caller: PriyaMemory | $0.001 |
| Look up order #5521 on ShopifyApps | $0.010 |
| Draft a reply with fast MistralModel | $0.001 |
| Speak the answerSpeech | $0.003 |
| One bill | $0.018 |
Run it with your own agent
- Get your key, then point your app’s OpenAI or Anthropic client at Flux. Quickstart
- Send the caller’s audio to Flux transcription. Transcription guide
- Ask flux-auto for a short reply, with the order details in the prompt, and speak the answer back.
What works today
- TranscriptionLiveTranscription works today. Send it an uploaded audio file.
- MemoryShippingMemory is shipping. Until then, put the preference in your agent’s instructions.
- AppsShippingApps on your own key are shipping. Until then, your agent can use its own tools for these steps, and Murage runs them today with apps built in.
- ModelLiveModel steps work today, as soon as your agent points at Flux with flux-auto.
- SpeechShippingSpeech is shipping. Until then, the answer comes back as text.
Questions
Do I need an agent for this?
No. This one is your own app calling Flux directly, with the same key and the same endpoints an agent would use.
Does every step work on my key today?
Not yet. Memory is shipping. Until then, put the preference in your agent’s instructions. Apps on your own key are shipping. Until then, your agent can use its own tools for these steps, and Murage runs them today with apps built in. Speech is shipping. Until then, the answer comes back as text. The steps marked Live work today.
What will it cost me?
The costs on this page are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay that model’s own rate instead. Web, image, voice and app steps have their own prices.
More jobs your agent can do
Give your agent everything else.
One key for every model and tool in this example.